Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    negative score differentials in sports contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Wunused
    -0.16
    çİ
    -0.15
    taire
    -0.14
    ogany
    -0.14
    enthal
    -0.14
    æĻ´
    -0.13
    ideshow
    -0.13
    lund
    -0.13
    ILA
    -0.13
     cÆ°á»Ŀng
    -0.13
    POSITIVE LOGITS
    iller
    0.15
    ardy
    0.15
     McGr
    0.14
     Interstate
    0.14
    appa
    0.13
     Hab
    0.13
    okies
    0.13
    pper
    0.13
     HoÃłng
    0.13
     ragaz
    0.13
    Act Density 0.094%

    No Known Activations